These days it is a cliché to point out that technology has changed our lives. But it has. It really has. Not only in terms of what we can do from the palm of our hand or the comfort of our living room. But also in terms of how we maintain and think about our social ties. How we think about the connections that define us. Technology has redefined today’s social world.
The same technology revolution is beginning to shape the behavioural sciences. A new field of ‘big data’ has emerged, and scientists are getting their teeth into the millions of journeys, clicks, and messages that are made, done, and sent every second of every day. So, what’s out there in this brave new world?
language provides a window into the emotional, cognitive and social life of the speaker
One prominent area of progress relates to language. The development of computer-based text analytics has made it possible to use language as a means of inferring a great deal about the psychology of writers. A number of labs around the world have mapped out the connections between the use of particular kinds of words and psychological states: positive and negative emotion, increased thinking, confusion, self-reflection, depression, and deceit. Deployed on Twitter feeds over time, for example, it is possible to gain a rich picture of somebody’s emotional and cognitive life. It is even possible to gauge a nation’s mood, such as in the days following 9/11, or the sentiments of communities, as occurred during the London riots.
When used to examine the individual, this method offers more than a simple description of the writer. For example, in an effort to provide children with a way to interact safely online, a research spin-out company known as ISIS have developed a tool that can identify adults posing as children in teenage chat rooms. This tool knows the language and grammar that is typical of adults, as well as the mistakes that adults make when trying to act as children. It monitors a child’s interaction, and flags a danger sign when the language being used contains the characteristics of an adult’s writing.
It is also possible to use more complex systems to automate an analysis of the semantic meaning of texts. A tool known as WMatrix provides a valuable way of accessing the kinds of concepts that are being associated with entities of interest. For example, it is possible to derive a high-level understanding of how the UK and the US are talked about on extremist forums. As it happens, this work has been done. To the researchers surprise, the UK and US are associated with some very different concepts. The relative perceptions of these countries are more subtle than a single ‘Evil West’.
WMatrix provides a way of assessing the kinds of concepts that are being associated with entities of interest
Another example of where technology has revolutionised our understanding is in relation to nonverbal behaviour. To capture nonverbal behaviour, researchers use wireless motion capture sensors that measure movement over the course of an interaction. There are various types. Some of the earliest work utilised Sparkfun’s WiTilt sensors, a matchbox sized package of accelerometers that was available from an amateur electronics store and designed for a very different purpose than measuring nonverbal behaviour. However, with a bit of tweaking and some software development, it was possible to obtain from these devices measurements of the extent to which, and direction in which, the device moved in space. This made it possible to measure a person’s behaviour over time by strapping the WiTilts onto various limbs and recording the output. Comparing these movement data across participants provides a measure of nonverbal mimicry.
Things have developed since then. Today researchers use a technology known as Xsens MVN. The Xsens MVN utilises a series of sensors distributed across the main limbs and joints of the body, which are warn using either a suit or a set of straps. The distribution of sensors tracks movement across the entire body and allows for almost perfect recording and reproduction of movement. Indeed, this is the technology that they use to make animated films such as the recent comedy Ted.
suspects increase their postural sway when responding to the object they were seeking to deny knowing
One interesting application of this technology develops what is known as the guilty knowledge test. Often associated with the polygraph, the guilty knowledge test presents a series of ‘stimuli’ to an interviewee one after another. One of these items is known to the interviewee and could only be known to him or her if they have ‘guilty knowledge.’ It might be the knife used at the murder scene, or the vehicle used to transport the bomb. The test looks to see if there is a change in the interviewee’s behaviour when they see the guilty knowledge item, which may reflect both recognition and a desire to suppress any outward sign of that recognition.
Consistent with this, recent work has shown that interviewees increase their postural sway when responding to the guilty knowledge item. What’s interesting about this finding is that the sway is too subtle to be spotted by the naked eye, meaning that it may have been overlooked in the past.
A second application of this technology focuses on interpersonal behaviour, using the sensors to measure nonverbal mimicry. The process of nonverbal mimicry may be defined as movements by one person that coincides with the timing and rhythm of the movements of their interaction partner. For example, behavioural mimicry may take the form of discrete movements such as matched touching of the face, or more continuous patterns of behaviour such as mutual changes in posture. This mutual coordination of behaviour typically occurs unconsciously and it is associated with increased cooperation and liking.
To capture this aspect of behaviour automatically requires two (or more) Xsens MVN suits. Each suit captures the movement of an individual, and comparisons across the suits provides a measure of behavioural matching. As an aside, it is enlightening to record and watch your own nonverbal behaviour using the Xsens MVN system, since our posture and gestures are not something we are typically aware of doing. This means that the Xsens MVN system can be a useful tool in training because it allows those tasked with gaining cooperation to review how they behave when interacting with others.
Those who are practically minded may be concerned that full Xsens MVN suits, while good for research, will be less practical when it comes to measuring the behaviour of a real suspect. However, the same technology that drives the measurements within an Xsens MVN suit are now in many mobile phones and, perhaps more importantly, they are readily integrated into devices that are no larger than an employee’s name badge. While the resolution of such devices is less sensitive and accurate than the Xsens MVN, and this inevitably limits their precision, they remain sensitive enough to capture broad changes in movement and movement mimicry. This not only makes them an attractive compromise for use in applied environments, but their relative low cost makes it possible to consider behaviour on a larger scale, such as within a group or across a whole organisation.
verbal mimicry can be measured remotely and used to gauge team cohesion, especially following an event or disruption
A number of researchers have used these devices to record behaviour in groups. They have shown that nonverbal activity and mimicry predicts the level of cooperation, task performance, and even sales pitch success. They have managed to define what a healthy group looks like and what a troubled group looks like. The devices thus provide a way of measuring the nature of a group’s performance, which may provide the impetus for an intervention that promotes change. Designers are already building this tech into real-time feedback systems for meetings. No longer simply toys, these technologies are soon to be part of our everyday work life.